embedding-condensation
Measure layer-wise token embedding cosine similarity, assessing the severity of embedding condensation. Concept from [ICML 2026] Dispersion loss counteracts embedding condensation and improves generalization in small language models.
embedding-condensation has been downloaded 5,678 times in total on PyPI, including 242 in the last 30 days. The latest version is 2.0, released May 17, 2026.
Version2.0
Downloads
5.68k
LicenseNon-Commercial License — see ../LICENSE.md in the LM-Dispersion repository.
AuthorChen Liu
Downloads
Weekly, last 90d.
Includes CI traffic.
VersionsTotal2.*1.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included3 / 5 series
Selected total1.88k
5.7kAll-time
242Last 30 days
16Last 24 h
<0.01/sPer second
Sponsored
Sponsorships keep pepy free to read
Version distribution
Share of downloads by released version. Computed over the last quarter.
- 0146.2%
2.0
467 downloadsDownloads46746.2% - 0222.8%
1.1
230 downloadsDownloads23022.8% - 0317.5%
1.0.0
177 downloadsDownloads17717.5% - 0413.5%
0.1.0
136 downloadsDownloads13613.5%
Guess the next day
Thirteen recent days of embedding-condensation downloads. Drag the green handle on the right to guess where day fourteen lands.